Merge branch 'odp_fixes' into hmm.git

From rdma.git

Jason Gunthorpe says:

====================
This is a collection of general cleanups for ODP to clarify some of the
flows around umem creation and use of the interval tree.
====================

The branch is based on v5.3-rc5 due to dependencies, and is being taken
into hmm.git due to dependencies in the next patches.

* odp_fixes:
  RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
  RDMA/mlx5: Use ib_umem_start instead of umem.address
  RDMA/core: Make invalidate_range a device operation
  RDMA/odp: Use kvcalloc for the dma_list and page_list
  RDMA/odp: Check for overflow when computing the umem_odp end
  RDMA/odp: Provide ib_umem_odp_release() to undo the allocs
  RDMA/odp: Split creating a umem_odp from ib_umem_get
  RDMA/odp: Make the three ways to create a umem_odp clear
  RMDA/odp: Consolidate umem_odp initialization
  RDMA/odp: Make it clearer when a umem is an implicit ODP umem
  RDMA/odp: Iterate over the whole rbtree directly
  RDMA/odp: Use the common interval tree library instead of generic
  RDMA/mlx5: Fix MR npages calculation for IB_ACCESS_HUGETLB

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 10 insertions, 12 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 44df66a98f2a..c77d1e3761a7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -88,9 +88,6 @@ struct scan_control {
 	/* Can pages be swapped as part of reclaim? */
 	unsigned int may_swap:1;
 
-	/* e.g. boosted watermark reclaim leaves slabs alone */
-	unsigned int may_shrinkslab:1;
-
 	/*
 	 * Cgroups are not reclaimed below their configured memory.low,
 	 * unless we threaten to OOM. If any cgroups are skipped due to
@@ -699,7 +696,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	unsigned long ret, freed = 0;
 	struct shrinker *shrinker;
 
-	if (!mem_cgroup_is_root(memcg))
+	/*
+	 * The root memcg might be allocated even though memcg is disabled
+	 * via "cgroup_disable=memory" boot parameter.  This could make
+	 * mem_cgroup_is_root() return false, then just run memcg slab
+	 * shrink, but skip global shrink.  This may result in premature
+	 * oom.
+	 */
+	if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
 		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
 
 	if (!down_read_trylock(&shrinker_rwsem))
@@ -2707,10 +2711,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
 			node_lru_pages += lru_pages;
 
-			if (sc->may_shrinkslab) {
-				shrink_slab(sc->gfp_mask, pgdat->node_id,
-				    memcg, sc->priority);
-			}
+			shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
+					sc->priority);
 
 			/* Record the group's reclaim efficiency */
 			vmpressure(sc->gfp_mask, memcg, false,
@@ -3187,7 +3189,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = 1,
-		.may_shrinkslab = 1,
 	};
 
 	/*
@@ -3231,7 +3232,6 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 		.may_unmap = 1,
 		.reclaim_idx = MAX_NR_ZONES - 1,
 		.may_swap = !noswap,
-		.may_shrinkslab = 1,
 	};
 	unsigned long lru_pages;
 
@@ -3279,7 +3279,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = may_swap,
-		.may_shrinkslab = 1,
 	};
 
 	set_task_reclaim_state(current, &sc.reclaim_state);
@@ -3591,7 +3590,6 @@ restart:
 		 */
 		sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
 		sc.may_swap = !nr_boost_reclaim;
-		sc.may_shrinkslab = !nr_boost_reclaim;
 
 		/*
 		 * Do some background aging of the anon list, to give